****************************************************************************** This file provides some explanations about several datasets used in the book: Qiu, P. (2005), ``Image Processing and Jump Regression Analysis,'' New York: John Wiley & Sons. All the datasets are saved in ascii (text) files. They can be downloaded from this site. In the book, names of some data files are not mentioned. But, from the brief introduction provided here, it should be easy to figure out which one is which. If there is any confusion, please forward your enquiries to the author by emails (qiu@stat.umn.edu), or to the publisher in the case the author can not be reached. Data files are listed alphabetically below. ****************************************************************************** ------------------------------------------------------------------------------ File name: circles.dat Used in: Chapter 5 Brief description: This file contains data of the original circles image. A noisy version of the circles image is shown in Figure 5.11(a) in the book. The image has 256x256 pixels. Gray levels are in the range [0,255]. In the data file, observations are listed by 17 columns, but the columns are meaningless here. When the data are read into your programs, the columns should be ignored, and the observa- tions should be read ROW BY ROW. You can read all data into a column, and then form a 256x256 matrix from the column, or read the data into a 256x256 matrix I downloaded this data from the Waterloo Research Group's web page: http://links.uwaterloo.ca/bragzone.base.html/ ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ File name: elevation.dat Used in: Chapter 5 Brief description: This file contains the original global topographical elevation data. A noisy version of the data is shown in Figure 5.3(a) in the book, as an image. The data are arranged in a single column in the file. The data resolution is 1 degree by 1 degree in latitude and longitude. So, if the data are arranged in a matrix, with latitude as rows and longitude as columns, then the size of the matrix is 360x181. The data should be read into your programs by latitude. Namely, the first 181 observations correspond to latitude=0 degree east, the second 181 observations correspond to latitude=1 degree east, and so on. ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ File name: lena.dat Used in: Chapters 1 and 6 Brief description: This file contains data of the original Lena image, which is shown in Figure 1.1 in the book. The image has 512x512 pixels. Gray levels are in the range [0,255]. In the data file, observations are listed by 17 columns, but the columns are meaningless here. When the data are read into your programs, the columns should be ignored, and the observations should be read ROW BY ROW. You can read all data into a column, and then form a 512x512 matrix from the column, or read the data into a 512x512 matrix directly. ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ File name: microarray.dat Used in: Chapters 4 and 6 Brief description: This file contains data of a single spot of a microarray image, which is shown in Figure 6.14(a) in the book. The image has 48x48 pixels. Gray levels are in the range [1,256]. In the data file, observations are listed as a 48x48 matrix. You can read all data into a column, and then form a 48x48 matrix from the column, or read the data into a 48x48 matrix directly. ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ File name: mountain.dat Used in: Chapter 7 Brief description: This file contains data of the original mountain image, part of which is shown in Figure 7.1(a) in the book. The original mountain image has 480x640 pixels. Gray levels are in the range [0,255]. Figure 7.1(a) shows a part of the image, corresponding to the first 480x480 pixels. In the data file, observations are listed by 17 columns, but the columns are meaningless here. When the data are read into your programs, the columns should be ignored, and the observations should be read ROW BY ROW. You can read all data into a column, and then form a 480x640 matrix from the column, or read the data into a 480x640 matrix directly. ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ File name: peppers.dat Used in: Chapter 6 Brief description: This file contains data of the original peppers image, which is shown in Figure 6.12(a) in the book. The image has 512x512 pixels. Gray levels are in the range [0,255]. In the data file, observations are listed by 17 columns, but the columns are meaningless here. When the data are read into your programs, the columns should be ignored, and the observations should be read ROW BY ROW. You can read all data into a column, and then form a 512x512 matrix from the column, or read the data into a 512x512 matrix directly. ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ File name: sar.dat Used in: Chapters 1 and 4 Brief description: This file contains data of the SAR image shown in Figure 1.2 in the book. The image has 512x512 pixels. Gray levels are in the range [0,255]. In the data file, observations are listed by 17 columns, but the columns are meaningless here. When the data are read into your programs, the columns should be ignored, and the observations should be read ROW BY ROW. You can read all data into a column, and then form a 512x512 matrix from the column, or read the data into a 512x512 matrix directly. I downloaded this data from: http://peipa.essex.ac.uk/ipa/pix/books/glasbey-horgan/ ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ File name: sea.dat Used in: Chapters 1, 2 and 3 Brief description: This file contains the December sea-level pressure data, observed by a Bombay weather station in India during 1921-1992. The data are shown in Figure 1.3 in the book. In the file, there are two columns: the first column denotes the years of observation, and the second column contains the observed sea-level pressures. This data are described in the paper: Qiu, P., and Yandell, B. (1998), ``A local polynomial jump detection algorithm in nonparametric regression,'' Technometrics, Vol. 40, 141-152. ------------------------------------------------------------------------------ ------------------------------------------------------------------------------ File name: sleep.dat Used in: Chapter 3 Brief description: This file contains the sleep data described in Problem 3.9 of the book. The file has two columns: the first column denotes the middle points of 288 5-minute intervals of a day, and the second column includes the averaged percentages of sleep time of the eight Brown Norway rats under a certain lighting condition. This data are described in the paper: Qiu, P., Chappell, R., Obermeyer, W., and Benca, R. (1999), ``Modelling daily and subdaily cycles in rat sleep data,'' Biometrics, Vol. 55, 930-935. ------------------------------------------------------------------------------